2024-06-30-diakonikolas24a.md

title	section	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Testable Learning of General Halfspaces with Adversarial Label Noise	Original Papers	We study the task of testable learning of general — not necessarily homogeneous — halfspaces with adversarial label noise with respect to the Gaussian distribution. In the testable learning framework, the goal is to develop a tester-learner such that if the data passes the tester, then one can trust the output of the robust learner on the data. Our main result is the first polynomial time tester-learner for general halfspaces that achieves dimension-independent misclassification error. At the heart of our approach is a new methodology to reduce testable learning of general halfspaces to testable learning of \snew{nearly} homogeneous halfspaces that may be of broader interest.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	diakonikolas24a	0	Testable Learning of General Halfspaces with Adversarial Label Noise	1308	1335	1308-1335	1308	false	Diakonikolas, Ilias and Kane, Daniel and Liu, Sihan and Zarifis, Nikos	given family Ilias Diakonikolas given family Daniel Kane given family Sihan Liu given family Nikos Zarifis	2024-06-30		Proceedings of Thirty Seventh Conference on Learning Theory	247	inproceedings	date-parts 2024 6 30	https://proceedings.mlr.press/v247/diakonikolas24a/diakonikolas24a.pdf